Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts
Published in HHAI 2025: 4th International Conference on Hybrid Human-Artificial Intelligence, 2025
Recommended citation: Sahler, K., & Jentzsch, S. (2025). Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts. In HHAI 2025: Proceedings of the 4th International Conference on Hybrid Human-Artificial Intelligence (Vol. 408, pp. 423-438). IOS Press. https://doi.org/10.3233/FAIA250659
This study compares Zero-Shot, Chain-of-Thought, and Few-Shot prompting strategies for steering emotional tone in text generated by large language models. It finds that carefully selected human-written Few-Shot examples provide effective sentiment control and can be a practical alternative to fine-tuning when task-specific data is limited.
Recommended citation: Sahler, K., & Jentzsch, S. (2025). Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts. In HHAI 2025: Proceedings of the 4th International Conference on Hybrid Human-Artificial Intelligence (Vol. 408, pp. 423-438). IOS Press.